{"id":"W2791039059","doi":"10.1007/978-3-319-77553-1_9","title":"Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Frame (networking); Process (computing); Code (set theory); Pixel; Graph; Machine learning; Theoretical computer science; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003300432,0.0004220574,0.0005435653,0.0004041751,0.0002906814,0.0005775404,0.0007835171,0.0004805649,0.006783182],"category_scores_gemma":[0.002549964,0.0002570692,0.0003109011,0.0003718267,0.0005277266,0.001302201,0.001126415,0.001057553,0.0005541082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006258234,"about_ca_system_score_gemma":0.0004408128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002936764,"about_ca_topic_score_gemma":0.004093599,"domain_scores_codex":[0.9998385,0.00005384739,0.000007070532,0.00004221591,0.00003874744,0.00001970748],"domain_scores_gemma":[0.9994802,0.0002760416,0.00003757922,0.00008640181,0.0000726751,0.00004715566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001898606,0.0000977163,0.0004059575,0.0001386029,0.00002161357,0.00008153532,0.0001344036,0.6360936,0.006118827,0.1181607,0.00624686,0.2323103],"study_design_scores_gemma":[0.000008828456,0.00002108822,0.00005778499,0.000008749475,0.000003275544,0.000009726847,0.00001139507,0.9343114,0.0007474711,0.06356777,0.001248286,0.000004139516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04371579,0.000389826,0.9453955,0.0002329749,0.0000949224,0.00004361351,0.00008459773,0.002061126,0.007981549],"genre_scores_gemma":[0.7294443,0.0003513749,0.2597354,0.0001370275,0.00004434373,0.0001157689,0.0001941215,0.0006908024,0.009286866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006783182,"threshold_uncertainty_score":0.02269202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01606880271556596,"score_gpt":0.2794028763550346,"score_spread":0.2633340736394687,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}